© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108157
    Prev
    Next
    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.35
    miss
    -0.27
     Middleware
    -0.26
     Starr
    -0.25
    åľ¨ä»ĸ
    -0.24
    LLLL
    -0.24
     ë¬¼ë¡ł
    -0.24
    —if
    -0.23
    Invocation
    -0.23
     Mori
    -0.23
    POSITIVE LOGITS
    ?v
    0.27
    ities
    0.26
    æijĨ
    0.25
    ?):
    0.25
    åĿŃ
    0.24
    imd
    0.23
     needed
    0.23
    ünd
    0.23
     they
    0.23
     hab
    0.23
    Activations Density 0.189%

    No Known Activations